SANI-ITA employs a rule-based approach to multi-spectral image classification and post-classification refinement, and GIS modeling in order to extract useful information from imagery collected from airborne or spaceborne platforms.

The software tools employed in the classification is based on a hierarchy of rules that describe the conditions under which a set of low level constituent information gets abstracted into defined variables and includes raster imagery, vector coverages, spatial models, external programs, and simple scalars.

An integral part of the image classification process involves the staff of SANI-ITA collecting spectral signatures of features that the software will then use to cluster the image into classes. Externally derived signatures that have been supplied by clients of SANI-ITA can also be used as additional input to the classification.